Paper: A Markov Language Learning Model For Finite Parameter Spaces

ACL ID P94-1024
Title A Markov Language Learning Model For Finite Parameter Spaces
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1994
Authors

This paper shows how to formally characterize lan- guage learning in a finite parameter space as a Markov structure, hnportant new language learning results fol- low directly: explicitly calculated sample complexity learning times under different input distribution as- sumptions (including CHILDES database language in- put) and learning regimes. We also briefly describe a new way to formally model (rapid) diachronic syntax change. BACKGROUND MOTIVATION: TRIGGERS AND LANGUAGE ACQUISITION Recently, several researchers, including Gibson and Wexler (1994), henceforth GW, Dresher and Kaye (1990); and Clark and Roberts (1993) have modeled language learning in a (finite) space whose grammars are characterized by a finite number of parameters or n- length Boolean-valued vectors. Many current lingu...